材料导报, 2015, 29(20): 43-63. doi: 10.11896/j.issn.1005-023X.2015.20.009
纤维增强二氧化硅气凝胶复合材料的制备和低温性能
马佳 1, , 铁水Si含量间接反映炉温的变化,模型预测精度低.以影响炉温的6个变量为输入变量,采用基于自组织的分布式RBF神经网络模型分别对铁水温度和铁水Si含量建立预测模型,先用自组织神经网络划分输入输出样本空间,然后对每个子空间建立RBF神经网络子网模型,再使用子网模型对测试样本集的同一个样本点进行预测,并以测试样本点对每一子空间的隶属度为权值,对子网预测值进行加权求和,得到最终预测值.对比使用同一输入变量数据的铁水温度和铁水Si含量的预测模型命中率,研究表明,高炉铁水温度的命中率更高,具有更好的炉温预测效果.","authors":[{"authorName":"崔桂梅","id":"823e5a55-5f8b-4513-8cb6-44ca83c55e09","originalAuthorName":"崔桂梅"},{"authorName":"程史","id":"d5d23cb6-bcd5-4a2b-8e0a-f3bf09a70421","originalAuthorName":"程史"}],"doi":"","fpage":"27","id":"8775d7b3-880d-4385-a6b3-2eb5964f16cb","issue":"6","journal":{"abbrevTitle":"GT","coverImgSrc":"journal/img/cover/GT.jpg","id":"27","issnPpub":"0449-749X","publisherId":"GT","title":"钢铁"},"keywords":[{"id":"71db12b4-4923-4823-b928-3cbfb47dc7cc","keyword":"铁水温度预测","originalKeyword":"铁水温度预测"},{"id":"f9405486-4916-48c9-86cc-d395cfafd5fb","keyword":"铁水Si含量预测","originalKeyword":"铁水Si含量预测"},{"id":"94af658d-5b33-431a-8ecc-c291ae97dbf7","keyword":"分布式建模","originalKeyword":"分布式建模"},{"id":"e882bdcf-ab9f-4435-9b9b-9d4c66533a01","keyword":"自组织神经网络","originalKeyword":"自组织神经网络"},{"id":"1eb11110-5e1e-4da7-8835-21b36baea7f8","keyword":"RBF神经网络","originalKeyword":"RBF神经网络"}],"language":"zh","publisherId":"gtyjxb201406006","title":"基于分布式神经网络模型的高炉炉温预测建模","volume":"26","year":"2014"},{"abstractinfo":"针对高炉炉温与铁水硅含量呈正相关而非严格的线性关系和机制建模的主观性以及其难以建立各变量之间隐含的数学关系等的不足,在数据挖掘理论的基础上,对海量的样本数据进行预处理和特征提取,然后以高炉铁水温度为研究对象,建立了基于TS模糊神经网络的高炉铁水温度预测模型.最后,应用某高炉数据进行模型验证,并将该模型与T-S模糊多元回归模型以及BP神经网络模型进行比较研究,仿真结果表明T-S模糊神经网络模型的有效性和优越性.","authors":[{"authorName":"崔桂梅","id":"315b89e8-007d-4841-81ee-8b64d8b55179","originalAuthorName":"崔桂梅"},{"authorName":"李静","id":"d0191f4e-b690-4287-a39a-b3e2577e8c6e","originalAuthorName":"李静"},{"authorName":"张勇","id":"f507b995-ca1d-4627-8067-b8f3698b1721","originalAuthorName":"张勇"},{"authorName":"李仲德","id":"51f1bfd3-b9ed-43f4-859a-fb029e9abeb6","originalAuthorName":"李仲德"},{"authorName":"马祥","id":"bbdb82ac-5823-4916-84e2-5892c6563d38","originalAuthorName":"马祥"}],"doi":"","fpage":"11","id":"002c2d11-b203-419b-93c3-738d45bfcf19","issue":"11","journal":{"abbrevTitle":"GT","coverImgSrc":"journal/img/cover/GT.jpg","id":"27","issnPpub":"0449-749X","publisherId":"GT","title":"钢铁"},"keywords":[{"id":"2a33a378-b8b7-48bc-a4ab-4485adabc176","keyword":"高炉铁水温度","originalKeyword":"高炉铁水温度"},{"id":"df984220-af29-4fb4-b4a7-abaacc965c78","keyword":"T-S模糊回归","originalKeyword":"T-S模糊回归"},{"id":"04109ebd-1e24-4123-a570-430e7f5c630c","keyword":"T-S模糊神经网络","originalKeyword":"T-S模糊神经网络"}],"language":"zh","publisherId":"gt201311002","title":"基于T-S模糊神经网络模型的高炉铁水温度预测建模","volume":"48","year":"2013"},{"abstractinfo":"针对高炉炉温铁水硅含量为预测对象的不确定性和高炉炉温单变量时间序列模型所含炉温输入信息量少、难以揭示各个变量之间的相互关系及变化规律的特点,以高炉铁水温度为研究对象,建立BP神经网络多元时间序列模型和T-S模糊神经网络多元时间序列模型.应用高炉实际数据做模型检验,结果表明,T-S模糊神经网络多元时间序列模型取得更好的命中率和预测精度.","authors":[{"authorName":"崔桂梅","id":"85fb0b18-71a0-470e-a062-6ac345b3c91c","originalAuthorName":"崔桂梅"},{"authorName":"李静","id":"9b91e5c9-4581-41d8-99c2-35bc9d8b128e","originalAuthorName":"李静"},{"authorName":"张勇","id":"cb3f9225-b7aa-4efe-b555-f1acff9c38c3","originalAuthorName":"张勇"},{"authorName":"卢俊慧","id":"b9dab3fb-5112-4310-b544-33a2d6a09ec7","originalAuthorName":"卢俊慧"},{"authorName":"马祥","id":"eef75256-49fb-4aca-9ef2-c81f23b44b11","originalAuthorName":"马祥"}],"doi":"","fpage":"33","id":"456ddb25-3ff0-48a8-9afc-791623614676","issue":"4","journal":{"abbrevTitle":"GTYJXB","coverImgSrc":"journal/img/cover/GTYJXB.jpg","id":"30","issnPpub":"1001-0963","publisherId":"GTYJXB","title":"钢铁研究学报"},"keywords":[{"id":"b7410699-834e-4625-8e15-6821685cb42c","keyword":"高炉铁水温度","originalKeyword":"高炉铁水温度"},{"id":"9115d565-314f-4fd2-beb5-e2e7629e3180","keyword":"多元时间序列","originalKeyword":"多元时间序列"},{"id":"6143fa11-8911-40e5-a31d-969716aa789a","keyword":"BP神经网络","originalKeyword":"BP神经网络"},{"id":"ce160315-565a-4f18-85d5-baa206860f48","keyword":"模糊神经网络","originalKeyword":"模糊神经网络"}],"language":"zh","publisherId":"gtyjxb201404007","title":"高炉铁水温度的多元时间序列建模和预测","volume":"26","year":"2014"},{"abstractinfo":"采用多元回归分析建立了60t中间罐内钢水温度-T中间罐/℃的预测模型:T中间罐=-66.7499+1.03196T-0.768236x1-0.00750014x2+0.232252t-0.606243t2-9.39124×10-6t3式中:T代表钢包到达回转台时钢水温度(℃);x1代表钢包浇注前搁置时间(min);x2代表中间罐烘烤时间(min);t代表钢包钢水浇注时间(min).对中间罐内预测温度统计分析结果表明,该模型的钢水温度预测值与实测值非常吻合.","authors":[{"authorName":"田建国","id":"bb12bfba-7a42-4d9d-b615-998bd6c6e824","originalAuthorName":"田建国"}],"doi":"10.3969/j.issn.1005-4006.2006.02.017","fpage":"43","id":"88a2a71f-65ea-4547-8f58-5ceda8d8f730","issue":"2","journal":{"abbrevTitle":"LZ","coverImgSrc":"journal/img/cover/LZ.jpg","id":"52","issnPpub":"1005-4006","publisherId":"LZ","title":"连铸"},"keywords":[{"id":"bfeb38d1-faea-4483-8935-b9d045e25a51","keyword":"","originalKeyword":""}],"language":"zh","publisherId":"lz200602017","title":"中间罐内钢水温度预测模型","volume":"","year":"2006"},{"abstractinfo":"通过研究高炉-转炉界面铁水运输过程温度的主要影响因素，确定了影响高炉-转炉界面铁水运输过程温度的参数，建立了基于Levenberg-Marquardt(LM)算法BP神经网络的高炉-转炉界面铁水温度及铁水过程温降的预报模型。用沙钢100包铁水数据进行模型训练，50包铁水数据进行现场预报，结果表明：在高炉-转炉界面“一包到底”模式下，当绝对误差│X│≤20℃时，铁水温度命中率为94%，铁水温降命中率为78%；当绝对误差│X│≤40℃时，铁水温度命中率为100%，铁水温降命中率为92%，该预报模型能够满足现场实际生产需求，对炼钢生产有很好的指导意义。","authors":[{"authorName":"任彦军","id":"e43c2f1c-06b4-4bdb-8561-e2b1827a4153","originalAuthorName":"任彦军"},{"authorName":"，王家伟，张晓兵，赵浩文","id":"2caad1ec-93a9-48fd-8a21-c1267853e074","originalAuthorName":"，王家伟，张晓兵，赵浩文"}],"categoryName":"|","doi":"","fpage":"40","id":"041296cc-db45-4233-8f6c-365be8ef4f18","issue":"9","journal":{"abbrevTitle":"GT","coverImgSrc":"journal/img/cover/GT.jpg","id":"27","issnPpub":"0449-749X","publisherId":"GT","title":"钢铁"},"keywords":[{"id":"823f01b7-e2ff-4361-9ac2-6185caf96ec1","keyword":"温度 ","originalKeyword":"温度 "},{"id":"5e96a188-b5af-41d5-87ec-6f1f7586458a","keyword":" BP neural network ","originalKeyword":" BP neural network "},{"id":"ffd941d1-b59a-49b1-9606-29e667062ba2","keyword":" LM algorithm ","originalKeyword":" LM algorithm "},{"id":"26d4c188-c308-43a0-bc00-ee4a71a0a23d","keyword":" predictive model","originalKeyword":" predictive model"}],"language":"zh","publisherId":"0449-749X_2012_9_16","title":"基于LM算法BP神经网络的高炉-转炉界面铁水温度预报模型","volume":"47","year":"2012"},{"abstractinfo":"通过研究高炉-转炉界面铁水运输过程温度的主要影响因素,确定了影响高炉-转炉界面铁水运输过程温度的参数,建立了基于Levenberg-Marquardt (LM)算法BP神经网络的高炉-转炉界面铁水温度及铁水过程温降的预报模型.用沙钢100包铁水数据进行模型训练,50包铁水数据进行现场预报,结果表明:在高炉-转炉界面“一包到底”模式下,当绝对误差| X |≤20℃时,铁水温度命中率为94％,铁水温降命中率为78％；当绝对误差|X|≤40℃时,铁水温度命中率为100％,铁水温降命中率为92％,该预报模型能够满足现场实际生产需求,对炼钢生产有很好的指导意义.","authors":[{"authorName":"任彦军","id":"5ffdacef-a9f6-43e7-a845-4d15d373d1bf","originalAuthorName":"任彦军"},{"authorName":"王家伟","id":"c05c8693-13f5-43bd-a97e-03abc3caf2ea","originalAuthorName":"王家伟"},{"authorName":"张晓兵","id":"eff2fe61-a3b8-4d6e-aed3-c8b666f5f9b6","originalAuthorName":"张晓兵"},{"authorName":"赵浩文","id":"01f360c6-cce5-4559-a5bf-99b72d03b1ba","originalAuthorName":"赵浩文"}],"doi":"","fpage":"40","id":"0f7b863b-1b5f-44d0-bf60-4b4bc1a314fc","issue":"9","journal":{"abbrevTitle":"GT","coverImgSrc":"journal/img/cover/GT.jpg","id":"27","issnPpub":"0449-749X","publisherId":"GT","title":"钢铁"},"keywords":[{"id":"fe7331db-fdd9-48f1-9bbb-fbd5c0a3f2e8","keyword":"温度","originalKeyword":"温度"},{"id":"951d9a49-9fcc-45c9-956a-5058ed028441","keyword":"BP神经网络","originalKeyword":"BP神经网络"},{"id":"93a4541e-c69a-4249-844b-5a14bff1b5e6","keyword":"LM算法","originalKeyword":"LM算法"},{"id":"4cd0da4c-e29c-4a0a-9125-8494e3f407e7","keyword":"预报模型","originalKeyword":"预报模型"}],"language":"zh","publisherId":"gt201209008","title":"基于LM算法BP神经网络的高炉-转炉界面铁水温度预报模型","volume":"47","year":"2012"},{"abstractinfo":"在研究攀钢连铸钢水温降规律的基础上，开发了连铸钢水温度预测模型。根据模型研究结果提出并实施了一系列温度控制措施，取得了中间包过热度小于25-℃的效果。","authors":[{"authorName":"么秋杨","id":"8c3fb9da-1d91-414c-8fd3-2a783c072bb4","originalAuthorName":"么秋杨"},{"authorName":"李炜","id":"acea76d7-766a-47b5-9b96-ece627a64be5","originalAuthorName":"李炜"},{"authorName":"陈永","id":"bb157534-8045-4f4a-b0c6-10b281679cba","originalAuthorName":"陈永"},{"authorName":"黄道鑫","id":"00a6df01-398d-4012-94e7-5aa8e9decc53","originalAuthorName":"黄道鑫"}],"doi":"10.3969/j.issn.1004-7638.2001.01.010","fpage":"53","id":"15263c1f-fd4a-4e6e-a9b3-7c026ccfca7c","issue":"1","journal":{"abbrevTitle":"GTFT","coverImgSrc":"journal/img/cover/gtft1.jpg","id":"28","issnPpub":"1004-7638","publisherId":"GTFT","title":"钢铁钒钛"},"keywords":[{"id":"19f19c5c-731d-42f6-b988-d526f8ecb28f","keyword":"连铸","originalKeyword":"连铸"},{"id":"f146182e-61cf-40d5-9ab6-2225cc92a902","keyword":"钢水","originalKeyword":"钢水"},{"id":"93c1baca-5b4a-42a0-8eb9-0d4abac65af5","keyword":"温度控制","originalKeyword":"温度控制"},{"id":"01ff2bdb-13d5-437d-975f-cceb4264eb79","keyword":"数学模型","originalKeyword":"数学模型"}],"language":"zh","publisherId":"gtft200101010","title":"攀钢连铸钢水温度预测模型及应用","volume":"22","year":"2001"},{"abstractinfo":"为了分析铁水在输送过程中的温降,开发了鱼雷罐中铁水温降数学模型.该模型已在宝钢实际使用,铁水温度的计算值与实测值吻合良好.利用该模型分析了各种因素对铁水温降的影响,讨论了减小铁水温降的措施.","authors":[{"authorName":"吴懋林","id":"36728daf-a5a6-4ca0-ad1b-a8bf72eafe4b","originalAuthorName":"吴懋林"},{"authorName":"张永宏","id":"4e401f36-5651-4e0c-82d2-cd5c275fad20","originalAuthorName":"张永宏"},{"authorName":"杨圣发","id":"737eec24-fa66-45c4-a953-9b63cafcc97e","originalAuthorName":"杨圣发"},{"authorName":"向顺华","id":"b1d0b1f7-d044-4d4d-ac2d-009bd603744c","originalAuthorName":"向顺华"},{"authorName":"刘铁树","id":"5e739b1e-2acd-46e0-84a6-2e08076f99e0","originalAuthorName":"刘铁树"},{"authorName":"孙国伟","id":"7817eced-d88d-4210-9079-3ff1c1f95f0b","originalAuthorName":"孙国伟"}],"doi":"","fpage":"12","id":"8141cd0f-e46f-4619-999d-08778eb6bdfa","issue":"4","journal":{"abbrevTitle":"GT","coverImgSrc":"journal/img/cover/GT.jpg","id":"27","issnPpub":"0449-749X","publisherId":"GT","title":"钢铁"},"keywords":[{"id":"1368af56-0aa3-4ebe-ad65-634a454e9130","keyword":"鱼雷罐","originalKeyword":"鱼雷罐"},{"id":"4d911d0b-1fbf-46fc-9fa7-f091d90434f1","keyword":"铁水温降","originalKeyword":"铁水温降"},{"id":"f6244d11-845e-4b3d-a30b-c63546f0bedb","keyword":"数值模拟","originalKeyword":"数值模拟"}],"language":"zh","publisherId":"gt200204003","title":"鱼雷罐铁水温降分析","volume":"37","year":"2002"},{"abstractinfo":"从热力学和动力学两方面探讨了铁水温度和Si含量对搅拌法脱硫的影响.结果表明,较低的温度可以降低平衡时铁水中的S含量,较高的温度则有利于提高S的传质速度.Si控制着铁水中的氧含量,促进脱硫反应的进行;Si含量的变化对脱硫后的平衡S含量影响不大.Si在脱硫反应生成的致密性高熔点2CaO·SiO2层包裹着石灰颗粒,阻碍了S在渣中的传质.","authors":[{"authorName":"刘飞","id":"450829dc-44d4-4d54-a505-c52cc1db0781","originalAuthorName":"刘飞"},{"authorName":"邹长东","id":"05e71f07-8b55-4b9f-a26e-9e9a26feeb6f","originalAuthorName":"邹长东"},{"authorName":"马建超","id":"14760fd3-2a1e-4880-8117-1e127896d96c","originalAuthorName":"马建超"}],"doi":"","fpage":"19","id":"eff32385-4454-4316-9aba-69926789630f","issue":"4","journal":{"abbrevTitle":"SHJS","coverImgSrc":"journal/img/cover/SHJS.jpg","id":"59","issnPpub":"1001-7208","publisherId":"SHJS","title":"上海金属"},"keywords":[{"id":"8e8d956a-2b95-4e67-8c8b-8734a3468efa","keyword":"铁水温度","originalKeyword":"铁水温度"},{"id":"5eb843e9-75d9-4d19-90e4-7de7beebb590","keyword":"Si含量","originalKeyword":"Si含量"},{"id":"5c3f7024-3e37-4e09-80f3-e7681f523b9b","keyword":"脱硫","originalKeyword":"脱硫"},{"id":"54ef05b8-c253-40ae-b10c-b8004c7752b4","keyword":"搅拌法","originalKeyword":"搅拌法"}],"language":"zh","publisherId":"shjs201404005","title":"铁水温度和硅含量对搅拌法脱硫的影响","volume":"36","year":"2014"},{"abstractinfo":"LF炉钢水温度的控制对钢的质量和连铸操作的顺行都很重要,而LF炉钢水温度的预报是LF炉钢水温度控制的前提.针对LF炉冶炼过程中物理化学反应过程及传热过程的复杂性,以宝山钢铁股份有限公司300 t LF炉为研究对象,在分析了影响LF炉钢水温度的主要因素的基础上,应用基于BP神经网络的信息融合算法,开发了用C语言编写的预测程序,预测了LF炉的钢水温度.实验表明,此算法可以提高预测的速度和精度,预测结果为误差不大于±5 ℃的炉次大于90%.","authors":[{"authorName":"王安娜","id":"43a39f7f-b343-434e-9745-ccf59d7b480a","originalAuthorName":"王安娜"},{"authorName":"田慧欣","id":"759250ee-ccf5-4a3c-8bac-14fe5dfacc92","originalAuthorName":"田慧欣"},{"authorName":"姜周华","id":"5351403f-4422-487d-b758-aab7e3f137b0","originalAuthorName":"姜周华"},{"authorName":"战东平","id":"5ea03622-c5b9-4000-aed3-cf487cd2a911","originalAuthorName":"战东平"},{"authorName":"尹小东","id":"4cda89c3-6abb-41b0-8073-6e8448fc5d6f","originalAuthorName":"尹小东"},{"authorName":"马志刚","id":"33b3f974-91e1-476d-a6e8-4196f73a175d","originalAuthorName":"马志刚"}],"doi":"","fpage":"71","id":"061e19ce-a1f8-4019-9117-f9269249de02","issue":"6","journal":{"abbrevTitle":"GTYJXB","coverImgSrc":"journal/img/cover/GTYJXB.jpg","id":"30","issnPpub":"1001-0963","publisherId":"GTYJXB","title":"钢铁研究学报"},"keywords":[{"id":"616b8cb6-f9a9-47a8-9d63-7457d07f3f2f","keyword":"LF","originalKeyword":"LF"},{"id":"d01a9374-9050-4678-9300-e8b515c992c2","keyword":"信息融合","originalKeyword":"信息融合"},{"id":"7f9eaedc-85a8-4544-b95c-4327d0d0e51f","keyword":"BP神经网络","originalKeyword":"BP神经网络"},{"id":"18719bd3-30b1-409b-940a-0843ef5d87f6","keyword":"Matlab","originalKeyword":"Matlab"},{"id":"c4d12f89-daa1-4028-a4f8-5d8cea757553","keyword":"钢水","originalKeyword":"钢水"},{"id":"518abad6-9912-48c4-b6ee-e9a62faf6336","keyword":"温度预测","originalKeyword":"温度预测"}],"language":"zh","publisherId":"gtyjxb200506017","title":"基于信息融合算法的LF炉钢水温度预测","volume":"17","year":"2005"}],"totalpage":5262,"totalrecord":52619}